AI Paper Atlas

Research map / Video / Video generation

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Hidir Yesiltepe, Tuna Meral, Adil Kaan Akan, Kaan Oktay, Pinar Yanardag

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 58 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase temporal jump index from 6 to 90 (ablation)Infinity-RoPE RoPE Cut · RoPE Cut, 40s videosBackground Consistency: 88.98 -> 82.27Hurt
increase temporal jump index from 6 to 90 (ablation)Infinity-RoPE RoPE Cut · RoPE Cut, 40s videosSubject Consistency: 90.74 -> 87.69Hurt
increase temporal jump index from 21 to 45 (outside training horizon) (ablation)Infinity-RoPE RoPE Cut · RoPE Cut, 40s videosBackground Consistency: 87.57 -> 84.48Hurt
increase temporal jump index from 6 to 90 (ablation)Infinity-RoPE RoPE Cut · RoPE Cut, 40s videosTemporal Smoothness: 0.98 -> 0.95Hurt
increase KV cache size (ablation)Infinity-RoPE · MovieGenBench long videosImaging Quality and Dynamic DegreeHurt
increase KV cache size (ablation)Infinity-RoPE · MovieGenBench long videosSubject and Background ConsistencyNo clear effect
replace Rolling-Forcing with Block-Relativistic RoPE on Self-ForcingRolling-Forcing · MovieGenBench 240s videosVBench Overall: 0.8017 -> 0.8309Improved
apply Block-Relativistic RoPE to Self-ForcingSelf-Forcing · MovieGenBench 240s videosVBench Overall: 0.6850 -> 0.8309Improved
apply Block-Relativistic RoPE to Self-ForcingSelf-Forcing · MovieGenBench 5s videosVBench Overall: 0.8398 -> 0.8377No clear effect
use KV Flush instead of KV-RecacheLongLive · User study, action-controlled generationText Alignment: 3.19 -> 3.86Improved
apply Infinity-RoPE instead of Rolling-Forcing for 60s videosRolling-Forcing · User study, 60s videosAverage Likert score: 3.488 -> 3.810Improved
apply Infinity-RoPE instead of Self-Forcing for 60s videosSelf-Forcing · MovieGenBench 60s videosVBench Overall: 0.7715 -> 0.8298Improved

Later papers that compared with this method

10 later accepted papers report Infinity-RoPE as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.

2 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy